Qwen/Qwen2-Math-72B-Instruct

Qwen/Qwen2-Math-72B-Instruct is a 72.7 billion parameter instruction-tuned causal language model developed by Qwen, specifically optimized for advanced mathematical and arithmetic problem-solving. Built upon the Qwen2 LLM series, this model significantly enhances reasoning capabilities for complex, multi-step logical mathematical tasks. It is designed to outperform other open-source and some closed-source models in mathematical performance, primarily supporting English for now.